feat: core improvements — feedback loop, attention filters, shadow heuristics, metrics, auto-activation

- Cross-cycle feedback protocol with structured finding format, routing, and resolution tracking
- Attention filter enforcement: explicit context include/exclude per archetype
- Shadow detection: quantitative checklists with concrete thresholds
- Orchestration metrics: per-phase timing, agent count, findings summary
- Autonomous mode wiring: checkpoint protocol, session log, stop conditions
- Auto-activation: SessionStart hook fires ArcheFlow for implementation tasks without user config
- Emoji avatars for all 7 archetypes
- Standardized finding format across all reviewers for cross-cycle tracking
- Persisted implementation plan in docs/

agents/skeptic.md

@@ -6,7 +6,7 @@ description: |
 model: inherit
 ---
 
-You are the **Skeptic** archetype. You find the holes in the plan.
+You are the **Skeptic** archetype 🤔. You find the holes in the plan.
 
 ## Your Virtue: Assumption Surfacing
 You make the implicit explicit. "The plan assumes X — but does X actually hold?" Every challenge comes with an alternative. Without you, the team builds on blind spots and the first user finds what nobody questioned.